Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1145 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3928. Min Range: -3.3928
Max Act: 3.3928. Min Act: -0.1700
Data Index: 7672038 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3928. Min Range: -3.3928
Max Act: 3.2358. Min Act: -0.1700
Data Index: 1162583 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3928. Min Range: -3.3928
Max Act: 3.2358. Min Act: -0.1700
Data Index: 6162623 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3928. Min Range: -3.3928
Max Act: 3.2044. Min Act: -0.1700
Data Index: 7793374 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3928. Min Range: -3.3928
Max Act: 3.1886. Min Act: -0.1700
Data Index: 6606716 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3928. Min Range: -3.3928
Max Act: 3.1729. Min Act: -0.1700
Data Index: 2991346 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3928. Min Range: -3.3928
Max Act: 3.1572. Min Act: -0.1700
Data Index: 7298980 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3928. Min Range: -3.3928
Max Act: 3.1572. Min Act: -0.1700
Data Index: 5254118 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3928. Min Range: -3.3928
Max Act: 3.1572. Min Act: -0.1700
Data Index: 21430 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3928. Min Range: -3.3928
Max Act: 3.1414. Min Act: -0.1700
Data Index: 2735643 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3928. Min Range: -3.3928
Max Act: 3.1257. Min Act: -0.1700
Data Index: 840099 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3928. Min Range: -3.3928
Max Act: 3.1414. Min Act: -0.1700
Data Index: 2141317 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3928. Min Range: -3.3928
Max Act: 3.1257. Min Act: -0.1700
Data Index: 2699330 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3928. Min Range: -3.3928
Max Act: 3.1257. Min Act: -0.1700
Data Index: 4885984 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3928. Min Range: -3.3928
Max Act: 3.1099. Min Act: -0.1700
Data Index: 5202707 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3928. Min Range: -3.3928
Max Act: 3.1099. Min Act: -0.1700
Data Index: 4220712 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3928. Min Range: -3.3928
Max Act: 3.1099. Min Act: -0.1700
Data Index: 1992588 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3928. Min Range: -3.3928
Max Act: 3.0942. Min Act: -0.1700
Data Index: 2459638 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3928. Min Range: -3.3928
Max Act: 3.0942. Min Act: -0.1700
Data Index: 4283372 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3928. Min Range: -3.3928
Max Act: 3.0784. Min Act: -0.1700
Data Index: 5602452 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19